pw code inference-servers

Manage inference server configurations saved locally on this machine

Synopsis

Manage named OpenAI-compatible inference servers whose configurations are saved locally for your user on this machine.

Profiles are stored in ~/.config/pw/inference-servers.json, or $XDG_CONFIG_HOME/pw/inference-servers.json when set. ACTIVATE does not store or synchronize these configurations. The inference server itself may run locally or remotely.

Run these commands on the machine hosting the pw code session. When attaching remotely, the session uses that host's saved configurations and credential sources. Tokens entered with --api-key are saved in that machine's OS credential store; profiles contain only credential references.

Select a model with inference-server/<name>/<model-id>.

pw code inference-servers [flags]

Options

  -h, --help   help for inference-servers

Options inherited from parent commands

      --context string         The context to use. Overrides PW_CONTEXT environment variable and current context from config.
      --platform-host string   The Parallel Works ACTIVATE platform host to use. Overrides PW_PLATFORM_HOST environment variable and the current context's server.
  -v, --verbose                Enable verbose logging

pw code inference-servers